# # See http://www.robotstxt.org/wc/norobots.html for documentation on how to use the robots.txt file # See http://www.searchtools.com/robots/robots-txt.html for search engine extensions # # See: # http://googlewebmastercentral.blogspot.com/2008/06/improving-on-robots-exclusion-protocol.html # for a nice summary of the REP (Robots Exclusion Protocol) and relevant META tags # # To ban all spiders from the entire site uncomment the next two lines: # User-Agent: * # Disallow: / # # User-agent: * # Disallow: /*page= # Disallow: /users/*/messages/new # ticket #162 : prevent "Googlebot" from spidering paginated pages on the site # ticket #170 : prevent "Googlebot" from spidering meaningless pages on the site # Google-specific wildcard extensions documented on the following pages: # http://www.google.com/support/webmasters/bin/answer.py?answer=76401&topic=8843 User-Agent: Googlebot Disallow: /*page= Disallow: /users/*/messages/new # ticket #162 : prevent "Yahoo! Slurp" from spidering paginated pages on the site # ticket #170 : prevent "Yahoo! Slurp" from spidering meaningless pages on the site # Google-specific wildcard extensions documented on the following pages: # http://help.yahoo.com/l/us/yahoo/search/webcrawler/slurp-02.html User-Agent: Slurp Disallow: /*page= Disallow: /users/*/messages/new # ticket #162 : prevent "M$ msnbot" from spidering paginated pages on the site # ticket #170 : prevent "M$ msnbot" from spidering meaningless pages on the site # Google-specific wildcard extensions documented on the following pages: # http://help.live.com/help.aspx?project=wl_webmasters&querytype=keyword&query=txtstobor&mkt=en-US User-Agent: msnbot Disallow: /*page= Disallow: /users/*/messages/new # ticket #162 : prevent "MJ12bot" from spidering paginated pages on the site # ticket #170 : prevent "MJ12bot" from spidering meaningless pages on the site # http://www.majestic12.co.uk/projects/dsearch/mj12bot.php#BlockBot # NOTE the wildcard extensions may or may not be implemented by MJ12bot, so # the following may or may not prevent the MJ12bot from spidering the site! User-Agent: MJ12bot Disallow: /*page= Disallow: /users/*/messages/new # ticket #162 : prevent "ia_archiver" from spidering paginated pages on the site # ticket #170 : prevent "ia_archiver" from spidering meaningless pages on the site # http://www.alexa.com/help/webmasters # NOTE the wildcard extensions may or may not be implemented by ia_archiver, so # the following may or may not prevent the ia_archiver from spidering the site! User-Agent: ia_archiver Disallow: /*page= Disallow: /users/*/messages/new